diff options
Diffstat (limited to 'arch/arm64/include')
32 files changed, 875 insertions, 288 deletions
diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h index 669028172fd6..a91933b1e2e6 100644 --- a/arch/arm64/include/asm/alternative.h +++ b/arch/arm64/include/asm/alternative.h @@ -5,6 +5,8 @@ #include <asm/cpucaps.h> #include <asm/insn.h> +#define ARM64_CB_PATCH ARM64_NCAPS + #ifndef __ASSEMBLY__ #include <linux/init.h> @@ -22,12 +24,19 @@ struct alt_instr { u8 alt_len; /* size of new instruction(s), <= orig_len */ }; +typedef void (*alternative_cb_t)(struct alt_instr *alt, + __le32 *origptr, __le32 *updptr, int nr_inst); + void __init apply_alternatives_all(void); void apply_alternatives(void *start, size_t length); -#define ALTINSTR_ENTRY(feature) \ +#define ALTINSTR_ENTRY(feature,cb) \ " .word 661b - .\n" /* label */ \ + " .if " __stringify(cb) " == 0\n" \ " .word 663f - .\n" /* new instruction */ \ + " .else\n" \ + " .word " __stringify(cb) "- .\n" /* callback */ \ + " .endif\n" \ " .hword " __stringify(feature) "\n" /* feature bit */ \ " .byte 662b-661b\n" /* source len */ \ " .byte 664f-663f\n" /* replacement len */ @@ -45,15 +54,18 @@ void apply_alternatives(void *start, size_t length); * but most assemblers die if insn1 or insn2 have a .inst. This should * be fixed in a binutils release posterior to 2.25.51.0.2 (anything * containing commit 4e4d08cf7399b606 or c1baaddf8861). + * + * Alternatives with callbacks do not generate replacement instructions. */ -#define __ALTERNATIVE_CFG(oldinstr, newinstr, feature, cfg_enabled) \ +#define __ALTERNATIVE_CFG(oldinstr, newinstr, feature, cfg_enabled, cb) \ ".if "__stringify(cfg_enabled)" == 1\n" \ "661:\n\t" \ oldinstr "\n" \ "662:\n" \ ".pushsection .altinstructions,\"a\"\n" \ - ALTINSTR_ENTRY(feature) \ + ALTINSTR_ENTRY(feature,cb) \ ".popsection\n" \ + " .if " __stringify(cb) " == 0\n" \ ".pushsection .altinstr_replacement, \"a\"\n" \ "663:\n\t" \ newinstr "\n" \ @@ -61,11 +73,17 @@ void apply_alternatives(void *start, size_t length); ".popsection\n\t" \ ".org . - (664b-663b) + (662b-661b)\n\t" \ ".org . - (662b-661b) + (664b-663b)\n" \ + ".else\n\t" \ + "663:\n\t" \ + "664:\n\t" \ + ".endif\n" \ ".endif\n" #define _ALTERNATIVE_CFG(oldinstr, newinstr, feature, cfg, ...) \ - __ALTERNATIVE_CFG(oldinstr, newinstr, feature, IS_ENABLED(cfg)) + __ALTERNATIVE_CFG(oldinstr, newinstr, feature, IS_ENABLED(cfg), 0) +#define ALTERNATIVE_CB(oldinstr, cb) \ + __ALTERNATIVE_CFG(oldinstr, "NOT_AN_INSTRUCTION", ARM64_CB_PATCH, 1, cb) #else #include <asm/assembler.h> @@ -132,6 +150,14 @@ void apply_alternatives(void *start, size_t length); 661: .endm +.macro alternative_cb cb + .set .Lasm_alt_mode, 0 + .pushsection .altinstructions, "a" + altinstruction_entry 661f, \cb, ARM64_CB_PATCH, 662f-661f, 0 + .popsection +661: +.endm + /* * Provide the other half of the alternative code sequence. */ @@ -158,6 +184,13 @@ void apply_alternatives(void *start, size_t length); .endm /* + * Callback-based alternative epilogue + */ +.macro alternative_cb_end +662: +.endm + +/* * Provides a trivial alternative or default sequence consisting solely * of NOPs. The number of NOPs is chosen automatically to match the * previous case. diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h index 9becba9ab392..e278f94df0c9 100644 --- a/arch/arm64/include/asm/arch_gicv3.h +++ b/arch/arm64/include/asm/arch_gicv3.h @@ -76,11 +76,6 @@ static inline u64 gic_read_iar_cavium_thunderx(void) return irqstat; } -static inline void gic_write_pmr(u32 val) -{ - write_sysreg_s(val, SYS_ICC_PMR_EL1); -} - static inline void gic_write_ctlr(u32 val) { write_sysreg_s(val, SYS_ICC_CTLR_EL1); diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h index 3c78835bba94..0bcc98dbba56 100644 --- a/arch/arm64/include/asm/assembler.h +++ b/arch/arm64/include/asm/assembler.h @@ -202,25 +202,15 @@ lr .req x30 // link register /* * Pseudo-ops for PC-relative adr/ldr/str <reg>, <symbol> where - * <symbol> is within the range +/- 4 GB of the PC when running - * in core kernel context. In module context, a movz/movk sequence - * is used, since modules may be loaded far away from the kernel - * when KASLR is in effect. + * <symbol> is within the range +/- 4 GB of the PC. */ /* * @dst: destination register (64 bit wide) * @sym: name of the symbol */ .macro adr_l, dst, sym -#ifndef MODULE adrp \dst, \sym add \dst, \dst, :lo12:\sym -#else - movz \dst, #:abs_g3:\sym - movk \dst, #:abs_g2_nc:\sym - movk \dst, #:abs_g1_nc:\sym - movk \dst, #:abs_g0_nc:\sym -#endif .endm /* @@ -231,7 +221,6 @@ lr .req x30 // link register * the address */ .macro ldr_l, dst, sym, tmp= -#ifndef MODULE .ifb \tmp adrp \dst, \sym ldr \dst, [\dst, :lo12:\sym] @@ -239,15 +228,6 @@ lr .req x30 // link register adrp \tmp, \sym ldr \dst, [\tmp, :lo12:\sym] .endif -#else - .ifb \tmp - adr_l \dst, \sym - ldr \dst, [\dst] - .else - adr_l \tmp, \sym - ldr \dst, [\tmp] - .endif -#endif .endm /* @@ -257,28 +237,18 @@ lr .req x30 // link register * while <src> needs to be preserved. */ .macro str_l, src, sym, tmp -#ifndef MODULE adrp \tmp, \sym str \src, [\tmp, :lo12:\sym] -#else - adr_l \tmp, \sym - str \src, [\tmp] -#endif .endm /* - * @dst: Result of per_cpu(sym, smp_processor_id()), can be SP for - * non-module code + * @dst: Result of per_cpu(sym, smp_processor_id()) (can be SP) * @sym: The name of the per-cpu variable * @tmp: scratch register */ .macro adr_this_cpu, dst, sym, tmp -#ifndef MODULE adrp \tmp, \sym add \dst, \tmp, #:lo12:\sym -#else - adr_l \dst, \sym -#endif alternative_if_not ARM64_HAS_VIRT_HOST_EXTN mrs \tmp, tpidr_el1 alternative_else @@ -595,4 +565,140 @@ USER(\label, ic ivau, \tmp2) // invalidate I line PoU #endif .endm + /* + * frame_push - Push @regcount callee saved registers to the stack, + * starting at x19, as well as x29/x30, and set x29 to + * the new value of sp. Add @extra bytes of stack space + * for locals. + */ + .macro frame_push, regcount:req, extra + __frame st, \regcount, \extra + .endm + + /* + * frame_pop - Pop the callee saved registers from the stack that were + * pushed in the most recent call to frame_push, as well + * as x29/x30 and any extra stack space that may have been + * allocated. + */ + .macro frame_pop + __frame ld + .endm + + .macro __frame_regs, reg1, reg2, op, num + .if .Lframe_regcount == \num + \op\()r \reg1, [sp, #(\num + 1) * 8] + .elseif .Lframe_regcount > \num + \op\()p \reg1, \reg2, [sp, #(\num + 1) * 8] + .endif + .endm + + .macro __frame, op, regcount, extra=0 + .ifc \op, st + .if (\regcount) < 0 || (\regcount) > 10 + .error "regcount should be in the range [0 ... 10]" + .endif + .if ((\extra) % 16) != 0 + .error "extra should be a multiple of 16 bytes" + .endif + .ifdef .Lframe_regcount + .if .Lframe_regcount != -1 + .error "frame_push/frame_pop may not be nested" + .endif + .endif + .set .Lframe_regcount, \regcount + .set .Lframe_extra, \extra + .set .Lframe_local_offset, ((\regcount + 3) / 2) * 16 + stp x29, x30, [sp, #-.Lframe_local_offset - .Lframe_extra]! + mov x29, sp + .endif + + __frame_regs x19, x20, \op, 1 + __frame_regs x21, x22, \op, 3 + __frame_regs x23, x24, \op, 5 + __frame_regs x25, x26, \op, 7 + __frame_regs x27, x28, \op, 9 + + .ifc \op, ld + .if .Lframe_regcount == -1 + .error "frame_push/frame_pop may not be nested" + .endif + ldp x29, x30, [sp], #.Lframe_local_offset + .Lframe_extra + .set .Lframe_regcount, -1 + .endif + .endm + +/* + * Check whether to yield to another runnable task from kernel mode NEON code + * (which runs with preemption disabled). + * + * if_will_cond_yield_neon + * // pre-yield patchup code + * do_cond_yield_neon + * // post-yield patchup code + * endif_yield_neon <label> + * + * where <label> is optional, and marks the point where execution will resume + * after a yield has been performed. If omitted, execution resumes right after + * the endif_yield_neon invocation. Note that the entire sequence, including + * the provided patchup code, will be omitted from the image if CONFIG_PREEMPT + * is not defined. + * + * As a convenience, in the case where no patchup code is required, the above + * sequence may be abbreviated to + * + * cond_yield_neon <label> + * + * Note that the patchup code does not support assembler directives that change + * the output section, any use of such directives is undefined. + * + * The yield itself consists of the following: + * - Check whether the preempt count is exactly 1, in which case disabling + * preemption once will make the task preemptible. If this is not the case, + * yielding is pointless. + * - Check whether TIF_NEED_RESCHED is set, and if so, disable and re-enable + * kernel mode NEON (which will trigger a reschedule), and branch to the + * yield fixup code. + * + * This macro sequence may clobber all CPU state that is not guaranteed by the + * AAPCS to be preserved across an ordinary function call. + */ + + .macro cond_yield_neon, lbl + if_will_cond_yield_neon + do_cond_yield_neon + endif_yield_neon \lbl + .endm + + .macro if_will_cond_yield_neon +#ifdef CONFIG_PREEMPT + get_thread_info x0 + ldr w1, [x0, #TSK_TI_PREEMPT] + ldr x0, [x0, #TSK_TI_FLAGS] + cmp w1, #PREEMPT_DISABLE_OFFSET + csel x0, x0, xzr, eq + tbnz x0, #TIF_NEED_RESCHED, .Lyield_\@ // needs rescheduling? + /* fall through to endif_yield_neon */ + .subsection 1 +.Lyield_\@ : +#else + .section ".discard.cond_yield_neon", "ax" +#endif + .endm + + .macro do_cond_yield_neon + bl kernel_neon_end + bl kernel_neon_begin + .endm + + .macro endif_yield_neon, lbl + .ifnb \lbl + b \lbl + .else + b .Lyield_out_\@ + .endif + .previous +.Lyield_out_\@ : + .endm + #endif /* __ASM_ASSEMBLER_H */ diff --git a/arch/arm64/include/asm/cache.h b/arch/arm64/include/asm/cache.h index ea9bb4e0e9bb..9bbffc7a301f 100644 --- a/arch/arm64/include/asm/cache.h +++ b/arch/arm64/include/asm/cache.h @@ -20,8 +20,12 @@ #define CTR_L1IP_SHIFT 14 #define CTR_L1IP_MASK 3 +#define CTR_DMINLINE_SHIFT 16 +#define CTR_ERG_SHIFT 20 #define CTR_CWG_SHIFT 24 #define CTR_CWG_MASK 15 +#define CTR_IDC_SHIFT 28 +#define CTR_DIC_SHIFT 29 #define CTR_L1IP(ctr) (((ctr) >> CTR_L1IP_SHIFT) & CTR_L1IP_MASK) diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h index bef9f418f089..0094c6653b06 100644 --- a/arch/arm64/include/asm/cacheflush.h +++ b/arch/arm64/include/asm/cacheflush.h @@ -133,14 +133,15 @@ extern void flush_dcache_page(struct page *); static inline void __flush_icache_all(void) { + if (cpus_have_const_cap(ARM64_HAS_CACHE_DIC)) + return; + asm("ic ialluis"); dsb(ish); } -#define flush_dcache_mmap_lock(mapping) \ - spin_lock_irq(&(mapping)->tree_lock) -#define flush_dcache_mmap_unlock(mapping) \ - spin_unlock_irq(&(mapping)->tree_lock) +#define flush_dcache_mmap_lock(mapping) do { } while (0) +#define flush_dcache_mmap_unlock(mapping) do { } while (0) /* * We don't appear to need to do anything here. In fact, if we did, we'd diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h index ae852add053d..4f5fd2a36e6e 100644 --- a/arch/arm64/include/asm/cmpxchg.h +++ b/arch/arm64/include/asm/cmpxchg.h @@ -18,7 +18,8 @@ #ifndef __ASM_CMPXCHG_H #define __ASM_CMPXCHG_H -#include <linux/bug.h> +#include <linux/build_bug.h> +#include <linux/compiler.h> #include <asm/atomic.h> #include <asm/barrier.h> @@ -196,32 +197,6 @@ __CMPXCHG_GEN(_mb) __ret; \ }) -/* this_cpu_cmpxchg */ -#define _protect_cmpxchg_local(pcp, o, n) \ -({ \ - typeof(*raw_cpu_ptr(&(pcp))) __ret; \ - preempt_disable(); \ - __ret = cmpxchg_local(raw_cpu_ptr(&(pcp)), o, n); \ - preempt_enable(); \ - __ret; \ -}) - -#define this_cpu_cmpxchg_1(ptr, o, n) _protect_cmpxchg_local(ptr, o, n) -#define this_cpu_cmpxchg_2(ptr, o, n) _protect_cmpxchg_local(ptr, o, n) -#define this_cpu_cmpxchg_4(ptr, o, n) _protect_cmpxchg_local(ptr, o, n) -#define this_cpu_cmpxchg_8(ptr, o, n) _protect_cmpxchg_local(ptr, o, n) - -#define this_cpu_cmpxchg_double_8(ptr1, ptr2, o1, o2, n1, n2) \ -({ \ - int __ret; \ - preempt_disable(); \ - __ret = cmpxchg_double_local( raw_cpu_ptr(&(ptr1)), \ - raw_cpu_ptr(&(ptr2)), \ - o1, o2, n1, n2); \ - preempt_enable(); \ - __ret; \ -}) - #define __CMPWAIT_CASE(w, sz, name) \ static inline void __cmpwait_case_##name(volatile void *ptr, \ unsigned long val) \ diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h index bb263820de13..bc51b72fafd4 100644 --- a/arch/arm64/include/asm/cpucaps.h +++ b/arch/arm64/include/asm/cpucaps.h @@ -32,7 +32,7 @@ #define ARM64_HAS_VIRT_HOST_EXTN 11 #define ARM64_WORKAROUND_CAVIUM_27456 12 #define ARM64_HAS_32BIT_EL0 13 -#define ARM64_HYP_OFFSET_LOW 14 +#define ARM64_HARDEN_EL2_VECTORS 14 #define ARM64_MISMATCHED_CACHE_LINE_SIZE 15 #define ARM64_HAS_NO_FPSIMD 16 #define ARM64_WORKAROUND_REPEAT_TLBI 17 @@ -43,9 +43,12 @@ #define ARM64_SVE 22 #define ARM64_UNMAP_KERNEL_AT_EL0 23 #define ARM64_HARDEN_BRANCH_PREDICTOR 24 -#define ARM64_HARDEN_BP_POST_GUEST_EXIT 25 -#define ARM64_HAS_RAS_EXTN 26 +#define ARM64_HAS_RAS_EXTN 25 +#define ARM64_WORKAROUND_843419 26 +#define ARM64_HAS_CACHE_IDC 27 +#define ARM64_HAS_CACHE_DIC 28 +#define ARM64_HW_DBM 29 -#define ARM64_NCAPS 27 +#define ARM64_NCAPS 30 #endif /* __ASM_CPUCAPS_H */ diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index 060e3a4008ab..09b0f2a80c8f 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -10,6 +10,7 @@ #define __ASM_CPUFEATURE_H #include <asm/cpucaps.h> +#include <asm/cputype.h> #include <asm/fpsimd.h> #include <asm/hwcap.h> #include <asm/sigcontext.h> @@ -89,24 +90,231 @@ struct arm64_ftr_reg { extern struct arm64_ftr_reg arm64_ftr_reg_ctrel0; -/* scope of capability check */ -enum { - SCOPE_SYSTEM, - SCOPE_LOCAL_CPU, -}; +/* + * CPU capabilities: + * + * We use arm64_cpu_capabilities to represent system features, errata work + * arounds (both used internally by kernel and tracked in cpu_hwcaps) and + * ELF HWCAPs (which are exposed to user). + * + * To support systems with heterogeneous CPUs, we need to make sure that we + * detect the capabilities correctly on the system and take appropriate + * measures to ensure there are no incompatibilities. + * + * This comment tries to explain how we treat the capabilities. + * Each capability has the following list of attributes : + * + * 1) Scope of Detection : The system detects a given capability by + * performing some checks at runtime. This could be, e.g, checking the + * value of a field in CPU ID feature register or checking the cpu + * model. The capability provides a call back ( @matches() ) to + * perform the check. Scope defines how the checks should be performed. + * There are three cases: + * + * a) SCOPE_LOCAL_CPU: check all the CPUs and "detect" if at least one + * matches. This implies, we have to run the check on all the + * booting CPUs, until the system decides that state of the + * capability is finalised. (See section 2 below) + * Or + * b) SCOPE_SYSTEM: check all the CPUs and "detect" if all the CPUs + * matches. This implies, we run the check only once, when the + * system decides to finalise the state of the capability. If the + * capability relies on a field in one of the CPU ID feature + * registers, we use the sanitised value of the register from the + * CPU feature infrastructure to make the decision. + * Or + * c) SCOPE_BOOT_CPU: Check only on the primary boot CPU to detect the + * feature. This category is for features that are "finalised" + * (or used) by the kernel very early even before the SMP cpus + * are brought up. + * + * The process of detection is usually denoted by "update" capability + * state in the code. + * + * 2) Finalise the state : The kernel should finalise the state of a + * capability at some point during its execution and take necessary + * actions if any. Usually, this is done, after all the boot-time + * enabled CPUs are brought up by the kernel, so that it can make + * better decision based on the available set of CPUs. However, there + * are some special cases, where the action is taken during the early + * boot by the primary boot CPU. (e.g, running the kernel at EL2 with + * Virtualisation Host Extensions). The kernel usually disallows any + * changes to the state of a capability once it finalises the capability + * and takes any action, as it may be impossible to execute the actions + * safely. A CPU brought up after a capability is "finalised" is + * referred to as "Late CPU" w.r.t the capability. e.g, all secondary + * CPUs are treated "late CPUs" for capabilities determined by the boot + * CPU. + * + * At the moment there are two passes of finalising the capabilities. + * a) Boot CPU scope capabilities - Finalised by primary boot CPU via + * setup_boot_cpu_capabilities(). + * b) Everything except (a) - Run via setup_system_capabilities(). + * + * 3) Verification: When a CPU is brought online (e.g, by user or by the + * kernel), the kernel should make sure that it is safe to use the CPU, + * by verifying that the CPU is compliant with the state of the + * capabilities finalised already. This happens via : + * + * secondary_start_kernel()-> check_local_cpu_capabilities() + * + * As explained in (2) above, capabilities could be finalised at + * different points in the execution. Each newly booted CPU is verified + * against the capabilities that have been finalised by the time it + * boots. + * + * a) SCOPE_BOOT_CPU : All CPUs are verified against the capability + * except for the primary boot CPU. + * + * b) SCOPE_LOCAL_CPU, SCOPE_SYSTEM: All CPUs hotplugged on by the + * user after the kernel boot are verified against the capability. + * + * If there is a conflict, the kernel takes an action, based on the + * severity (e.g, a CPU could be prevented from booting or cause a + * kernel panic). The CPU is allowed to "affect" the state of the + * capability, if it has not been finalised already. See section 5 + * for more details on conflicts. + * + * 4) Action: As mentioned in (2), the kernel can take an action for each + * detected capability, on all CPUs on the system. Appropriate actions + * include, turning on an architectural feature, modifying the control + * registers (e.g, SCTLR, TCR etc.) or patching the kernel via + * alternatives. The kernel patching is batched and performed at later + * point. The actions are always initiated only after the capability + * is finalised. This is usally denoted by "enabling" the capability. + * The actions are initiated as follows : + * a) Action is triggered on all online CPUs, after the capability is + * finalised, invoked within the stop_machine() context from + * enable_cpu_capabilitie(). + * + * b) Any late CPU, brought up after (1), the action is triggered via: + * + * check_local_cpu_capabilities() -> verify_local_cpu_capabilities() + * + * 5) Conflicts: Based on the state of the capability on a late CPU vs. + * the system state, we could have the following combinations : + * + * x-----------------------------x + * | Type | System | Late CPU | + * |-----------------------------| + * | a | y | n | + * |-----------------------------| + * | b | n | y | + * x-----------------------------x + * + * Two separate flag bits are defined to indicate whether each kind of + * conflict can be allowed: + * ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU - Case(a) is allowed + * ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU - Case(b) is allowed + * + * Case (a) is not permitted for a capability that the system requires + * all CPUs to have in order for the capability to be enabled. This is + * typical for capabilities that represent enhanced functionality. + * + * Case (b) is not permitted for a capability that must be enabled + * during boot if any CPU in the system requires it in order to run + * safely. This is typical for erratum work arounds that cannot be + * enabled after the corresponding capability is finalised. + * + * In some non-typical cases either both (a) and (b), or neither, + * should be permitted. This can be described by including neither + * or both flags in the capability's type field. + */ + + +/* + * Decide how the capability is detected. + * On any local CPU vs System wide vs the primary boot CPU + */ +#define ARM64_CPUCAP_SCOPE_LOCAL_CPU ((u16)BIT(0)) +#define ARM64_CPUCAP_SCOPE_SYSTEM ((u16)BIT(1)) +/* + * The capabilitiy is detected on the Boot CPU and is used by kernel + * during early boot. i.e, the capability should be "detected" and + * "enabled" as early as possibly on all booting CPUs. + */ +#define ARM64_CPUCAP_SCOPE_BOOT_CPU ((u16)BIT(2)) +#define ARM64_CPUCAP_SCOPE_MASK \ + (ARM64_CPUCAP_SCOPE_SYSTEM | \ + ARM64_CPUCAP_SCOPE_LOCAL_CPU | \ + ARM64_CPUCAP_SCOPE_BOOT_CPU) + +#define SCOPE_SYSTEM ARM64_CPUCAP_SCOPE_SYSTEM +#define SCOPE_LOCAL_CPU ARM64_CPUCAP_SCOPE_LOCAL_CPU +#define SCOPE_BOOT_CPU ARM64_CPUCAP_SCOPE_BOOT_CPU +#define SCOPE_ALL ARM64_CPUCAP_SCOPE_MASK + +/* + * Is it permitted for a late CPU to have this capability when system + * hasn't already enabled it ? + */ +#define ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU ((u16)BIT(4)) +/* Is it safe for a late CPU to miss this capability when system has it */ +#define ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU ((u16)BIT(5)) + +/* + * CPU errata workarounds that need to be enabled at boot time if one or + * more CPUs in the system requires it. When one of these capabilities + * has been enabled, it is safe to allow any CPU to boot that doesn't + * require the workaround. However, it is not safe if a "late" CPU + * requires a workaround and the system hasn't enabled it already. + */ +#define ARM64_CPUCAP_LOCAL_CPU_ERRATUM \ + (ARM64_CPUCAP_SCOPE_LOCAL_CPU | ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU) +/* + * CPU feature detected at boot time based on system-wide value of a + * feature. It is safe for a late CPU to have this feature even though + * the system hasn't enabled it, although the featuer will not be used + * by Linux in this case. If the system has enabled this feature already, + * then every late CPU must have it. + */ +#define ARM64_CPUCAP_SYSTEM_FEATURE \ + (ARM64_CPUCAP_SCOPE_SYSTEM | ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU) +/* + * CPU feature detected at boot time based on feature of one or more CPUs. + * All possible conflicts for a late CPU are ignored. + */ +#define ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE \ + (ARM64_CPUCAP_SCOPE_LOCAL_CPU | \ + ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU | \ + ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU) + +/* + * CPU feature detected at boot time, on one or more CPUs. A late CPU + * is not allowed to have the capability when the system doesn't have it. + * It is Ok for a late CPU to miss the feature. + */ +#define ARM64_CPUCAP_BOOT_RESTRICTED_CPU_LOCAL_FEATURE \ + (ARM64_CPUCAP_SCOPE_LOCAL_CPU | \ + ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU) + +/* + * CPU feature used early in the boot based on the boot CPU. All secondary + * CPUs must match the state of the capability as detected by the boot CPU. + */ +#define ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE ARM64_CPUCAP_SCOPE_BOOT_CPU struct arm64_cpu_capabilities { const char *desc; u16 capability; - int def_scope; /* default scope */ + u16 type; bool (*matches)(const struct arm64_cpu_capabilities *caps, int scope); - int (*enable)(void *); /* Called on all active CPUs */ + /* + * Take the appropriate actions to enable this capability for this CPU. + * For each successfully booted CPU, this method is called for each + * globally detected capability. + */ + void (*cpu_enable)(const struct arm64_cpu_capabilities *cap); union { struct { /* To be used for erratum handling only */ - u32 midr_model; - u32 midr_range_min, midr_range_max; + struct midr_range midr_range; + const struct arm64_midr_revidr { + u32 midr_rv; /* revision/variant */ + u32 revidr_mask; + } * const fixed_revs; }; + const struct midr_range *midr_range_list; struct { /* Feature register checking */ u32 sys_reg; u8 field_pos; @@ -115,9 +323,38 @@ struct arm64_cpu_capabilities { bool sign; unsigned long hwcap; }; + /* + * A list of "matches/cpu_enable" pair for the same + * "capability" of the same "type" as described by the parent. + * Only matches(), cpu_enable() and fields relevant to these + * methods are significant in the list. The cpu_enable is + * invoked only if the corresponding entry "matches()". + * However, if a cpu_enable() method is associated + * with multiple matches(), care should be taken that either + * the match criteria are mutually exclusive, or that the + * method is robust against being called multiple times. + */ + const struct arm64_cpu_capabilities *match_list; }; }; +static inline int cpucap_default_scope(const struct arm64_cpu_capabilities *cap) +{ + return cap->type & ARM64_CPUCAP_SCOPE_MASK; +} + +static inline bool +cpucap_late_cpu_optional(const struct arm64_cpu_capabilities *cap) +{ + return !!(cap->type & ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU); +} + +static inline bool +cpucap_late_cpu_permitted(const struct arm64_cpu_capabilities *cap) +{ + return !!(cap->type & ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU); +} + extern DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS); extern struct static_key_false cpu_hwcap_keys[ARM64_NCAPS]; extern struct static_key_false arm64_const_caps_ready; @@ -236,15 +473,8 @@ static inline bool id_aa64pfr0_sve(u64 pfr0) } void __init setup_cpu_features(void); - -void update_cpu_capabilities(const struct arm64_cpu_capabilities *caps, - const char *info); -void enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps); void check_local_cpu_capabilities(void); -void update_cpu_errata_workarounds(void); -void __init enable_errata_workarounds(void); -void verify_local_cpu_errata_workarounds(void); u64 read_sanitised_ftr_reg(u32 id); diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h index 350c76a1d15b..30014a9f8f2b 100644 --- a/arch/arm64/include/asm/cputype.h +++ b/arch/arm64/include/asm/cputype.h @@ -83,6 +83,8 @@ #define ARM_CPU_PART_CORTEX_A53 0xD03 #define ARM_CPU_PART_CORTEX_A73 0xD09 #define ARM_CPU_PART_CORTEX_A75 0xD0A +#define ARM_CPU_PART_CORTEX_A35 0xD04 +#define ARM_CPU_PART_CORTEX_A55 0xD05 #define APM_CPU_PART_POTENZA 0x000 @@ -102,6 +104,8 @@ #define MIDR_CORTEX_A72 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A72) #define MIDR_CORTEX_A73 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A73) #define MIDR_CORTEX_A75 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A75) +#define MIDR_CORTEX_A35 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A35) +#define MIDR_CORTEX_A55 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A55) #define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX) #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX) #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX) @@ -118,6 +122,45 @@ #define read_cpuid(reg) read_sysreg_s(SYS_ ## reg) /* + * Represent a range of MIDR values for a given CPU model and a + * range of variant/revision values. + * + * @model - CPU model as defined by MIDR_CPU_MODEL + * @rv_min - Minimum value for the revision/variant as defined by + * MIDR_CPU_VAR_REV + * @rv_max - Maximum value for the variant/revision for the range. + */ +struct midr_range { + u32 model; + u32 rv_min; + u32 rv_max; +}; + +#define MIDR_RANGE(m, v_min, r_min, v_max, r_max) \ + { \ + .model = m, \ + .rv_min = MIDR_CPU_VAR_REV(v_min, r_min), \ + .rv_max = MIDR_CPU_VAR_REV(v_max, r_max), \ + } + +#define MIDR_ALL_VERSIONS(m) MIDR_RANGE(m, 0, 0, 0xf, 0xf) + +static inline bool is_midr_in_range(u32 midr, struct midr_range const *range) +{ + return MIDR_IS_CPU_MODEL_RANGE(midr, range->model, + range->rv_min, range->rv_max); +} + +static inline bool +is_midr_in_range_list(u32 midr, struct midr_range const *ranges) +{ + while (ranges->model) + if (is_midr_in_range(midr, ranges++)) + return true; + return false; +} + +/* * The CPU ID never changes at run time, so we might as well tell the * compiler that it's constant. Use this function to read the CPU ID * rather than directly reading processor_id or read_cpuid() directly. diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h index 803443d74926..ce70c3ffb993 100644 --- a/arch/arm64/include/asm/esr.h +++ b/arch/arm64/include/asm/esr.h @@ -240,6 +240,15 @@ (((e) & ESR_ELx_SYS64_ISS_OP2_MASK) >> \ ESR_ELx_SYS64_ISS_OP2_SHIFT)) +/* + * ISS field definitions for floating-point exception traps + * (FP_EXC_32/FP_EXC_64). + * + * (The FPEXC_* constants are used instead for common bits.) + */ + +#define ESR_ELx_FP_EXC_TFV (UL(1) << 23) + #ifndef __ASSEMBLY__ #include <asm/types.h> diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h index 8857a0f0d0f7..aa7162ae93e3 100644 --- a/arch/arm64/include/asm/fpsimd.h +++ b/arch/arm64/include/asm/fpsimd.h @@ -22,33 +22,9 @@ #ifndef __ASSEMBLY__ #include <linux/cache.h> +#include <linux/init.h> #include <linux/stddef.h> -/* - * FP/SIMD storage area has: - * - FPSR and FPCR - * - 32 128-bit data registers - * - * Note that user_fpsimd forms a prefix of this structure, which is - * relied upon in the ptrace FP/SIMD accessors. - */ -struct fpsimd_state { - union { - struct user_fpsimd_state user_fpsimd; - struct { - __uint128_t vregs[32]; - u32 fpsr; - u32 fpcr; - /* - * For ptrace compatibility, pad to next 128-bit - * boundary here if extending this struct. - */ - }; - }; - /* the id of the last cpu to have restored this state */ - unsigned int cpu; -}; - #if defined(__KERNEL__) && defined(CONFIG_COMPAT) /* Masks for extracting the FPSR and FPCR from the FPSCR */ #define VFP_FPSCR_STAT_MASK 0xf800009f @@ -62,8 +38,8 @@ struct fpsimd_state { struct task_struct; -extern void fpsimd_save_state(struct fpsimd_state *state); -extern void fpsimd_load_state(struct fpsimd_state *state); +extern void fpsimd_save_state(struct user_fpsimd_state *state); +extern void fpsimd_load_state(struct user_fpsimd_state *state); extern void fpsimd_thread_switch(struct task_struct *next); extern void fpsimd_flush_thread(void); @@ -83,7 +59,9 @@ extern void sve_save_state(void *state, u32 *pfpsr); extern void sve_load_state(void const *state, u32 const *pfpsr, unsigned long vq_minus_1); extern unsigned int sve_get_vl(void); -extern int sve_kernel_enable(void *); + +struct arm64_cpu_capabilities; +extern void sve_kernel_enable(const struct arm64_cpu_capabilities *__unused); extern int __ro_after_init sve_max_vl; diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h index 4214c38d016b..f62c56b1793f 100644 --- a/arch/arm64/include/asm/insn.h +++ b/arch/arm64/include/asm/insn.h @@ -70,6 +70,7 @@ enum aarch64_insn_imm_type { AARCH64_INSN_IMM_6, AARCH64_INSN_IMM_S, AARCH64_INSN_IMM_R, + AARCH64_INSN_IMM_N, AARCH64_INSN_IMM_MAX }; @@ -314,6 +315,11 @@ __AARCH64_INSN_FUNCS(eor, 0x7F200000, 0x4A000000) __AARCH64_INSN_FUNCS(eon, 0x7F200000, 0x4A200000) __AARCH64_INSN_FUNCS(ands, 0x7F200000, 0x6A000000) __AARCH64_INSN_FUNCS(bics, 0x7F200000, 0x6A200000) +__AARCH64_INSN_FUNCS(and_imm, 0x7F800000, 0x12000000) +__AARCH64_INSN_FUNCS(orr_imm, 0x7F800000, 0x32000000) +__AARCH64_INSN_FUNCS(eor_imm, 0x7F800000, 0x52000000) +__AARCH64_INSN_FUNCS(ands_imm, 0x7F800000, 0x72000000) +__AARCH64_INSN_FUNCS(extr, 0x7FA00000, 0x13800000) __AARCH64_INSN_FUNCS(b, 0xFC000000, 0x14000000) __AARCH64_INSN_FUNCS(bl, 0xFC000000, 0x94000000) __AARCH64_INSN_FUNCS(cbz, 0x7F000000, 0x34000000) @@ -423,6 +429,16 @@ u32 aarch64_insn_gen_logical_shifted_reg(enum aarch64_insn_register dst, int shift, enum aarch64_insn_variant variant, enum aarch64_insn_logic_type type); +u32 aarch64_insn_gen_logical_immediate(enum aarch64_insn_logic_type type, + enum aarch64_insn_variant variant, + enum aarch64_insn_register Rn, + enum aarch64_insn_register Rd, + u64 imm); +u32 aarch64_insn_gen_extr(enum aarch64_insn_variant variant, + enum aarch64_insn_register Rm, + enum aarch64_insn_register Rn, + enum aarch64_insn_register Rd, + u8 lsb); u32 aarch64_insn_gen_prefetch(enum aarch64_insn_register base, enum aarch64_insn_prfm_type type, enum aarch64_insn_prfm_target target, diff --git a/arch/arm64/include/asm/kvm_arm.h b/arch/arm64/include/asm/kvm_arm.h index b0c84171e6a3..6dd285e979c9 100644 --- a/arch/arm64/include/asm/kvm_arm.h +++ b/arch/arm64/include/asm/kvm_arm.h @@ -25,6 +25,7 @@ /* Hyp Configuration Register (HCR) bits */ #define HCR_TEA (UL(1) << 37) #define HCR_TERR (UL(1) << 36) +#define HCR_TLOR (UL(1) << 35) #define HCR_E2H (UL(1) << 34) #define HCR_ID (UL(1) << 33) #define HCR_CD (UL(1) << 32) @@ -64,6 +65,7 @@ /* * The bits we set in HCR: + * TLOR: Trap LORegion register accesses * RW: 64bit by default, can be overridden for 32bit VMs * TAC: Trap ACTLR * TSC: Trap SMC @@ -81,9 +83,9 @@ */ #define HCR_GUEST_FLAGS (HCR_TSC | HCR_TSW | HCR_TWE | HCR_TWI | HCR_VM | \ HCR_TVM | HCR_BSU_IS | HCR_FB | HCR_TAC | \ - HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW) + HCR_AMO | HCR_SWIO | HCR_TIDCP | HCR_RW | HCR_TLOR | \ + HCR_FMO | HCR_IMO) #define HCR_VIRT_EXCP_MASK (HCR_VSE | HCR_VI | HCR_VF) -#define HCR_INT_OVERRIDE (HCR_FMO | HCR_IMO) #define HCR_HOST_VHE_FLAGS (HCR_RW | HCR_TGE | HCR_E2H) /* TCR_EL2 Registers bits */ diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index 24961b732e65..f6648a3e4152 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -33,6 +33,7 @@ #define KVM_ARM64_DEBUG_DIRTY_SHIFT 0 #define KVM_ARM64_DEBUG_DIRTY (1 << KVM_ARM64_DEBUG_DIRTY_SHIFT) +/* Translate a kernel address of @sym into its equivalent linear mapping */ #define kvm_ksym_ref(sym) \ ({ \ void *val = &sym; \ @@ -57,7 +58,9 @@ extern void __kvm_tlb_flush_local_vmid(struct kvm_vcpu *vcpu); extern void __kvm_timer_set_cntvoff(u32 cntvoff_low, u32 cntvoff_high); -extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu); +extern int kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu); + +extern int __kvm_vcpu_run_nvhe(struct kvm_vcpu *vcpu); extern u64 __vgic_v3_get_ich_vtr_el2(void); extern u64 __vgic_v3_read_vmcr(void); @@ -68,7 +71,19 @@ extern u32 __kvm_get_mdcr_el2(void); extern u32 __init_stage2_translation(void); -extern void __qcom_hyp_sanitize_btac_predictors(void); +#else /* __ASSEMBLY__ */ + +.macro get_host_ctxt reg, tmp + adr_l \reg, kvm_host_cpu_state + mrs \tmp, tpidr_el2 + add \reg, \reg, \tmp +.endm + +.macro get_vcpu_ptr vcpu, ctxt + get_host_ctxt \ctxt, \vcpu + ldr \vcpu, [\ctxt, #HOST_CONTEXT_VCPU] + kern_hyp_va \vcpu +.endm #endif diff --git a/arch/arm64/include/asm/kvm_emulate.h b/arch/arm64/include/asm/kvm_emulate.h index 413dc82b1e89..23b33e8ea03a 100644 --- a/arch/arm64/include/asm/kvm_emulate.h +++ b/arch/arm64/include/asm/kvm_emulate.h @@ -26,13 +26,15 @@ #include <asm/esr.h> #include <asm/kvm_arm.h> +#include <asm/kvm_hyp.h> #include <asm/kvm_mmio.h> #include <asm/ptrace.h> #include <asm/cputype.h> #include <asm/virt.h> unsigned long *vcpu_reg32(const struct kvm_vcpu *vcpu, u8 reg_num); -unsigned long *vcpu_spsr32(const struct kvm_vcpu *vcpu); +unsigned long vcpu_read_spsr32(const struct kvm_vcpu *vcpu); +void vcpu_write_spsr32(struct kvm_vcpu *vcpu, unsigned long v); bool kvm_condition_valid32(const struct kvm_vcpu *vcpu); void kvm_skip_instr32(struct kvm_vcpu *vcpu, bool is_wide_instr); @@ -45,6 +47,11 @@ void kvm_inject_undef32(struct kvm_vcpu *vcpu); void kvm_inject_dabt32(struct kvm_vcpu *vcpu, unsigned long addr); void kvm_inject_pabt32(struct kvm_vcpu *vcpu, unsigned long addr); +static inline bool vcpu_el1_is_32bit(struct kvm_vcpu *vcpu) +{ + return !(vcpu->arch.hcr_el2 & HCR_RW); +} + static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu) { vcpu->arch.hcr_el2 = HCR_GUEST_FLAGS; @@ -59,16 +66,19 @@ static inline void vcpu_reset_hcr(struct kvm_vcpu *vcpu) if (test_bit(KVM_ARM_VCPU_EL1_32BIT, vcpu->arch.features)) vcpu->arch.hcr_el2 &= ~HCR_RW; -} -static inline unsigned long vcpu_get_hcr(struct kvm_vcpu *vcpu) -{ - return vcpu->arch.hcr_el2; + /* + * TID3: trap feature register accesses that we virtualise. + * For now this is conditional, since no AArch32 feature regs + * are currently virtualised. + */ + if (!vcpu_el1_is_32bit(vcpu)) + vcpu->arch.hcr_el2 |= HCR_TID3; } -static inline void vcpu_set_hcr(struct kvm_vcpu *vcpu, unsigned long hcr) +static inline unsigned long *vcpu_hcr(struct kvm_vcpu *vcpu) { - vcpu->arch.hcr_el2 = hcr; + return (unsigned long *)&vcpu->arch.hcr_el2; } static inline void vcpu_set_vsesr(struct kvm_vcpu *vcpu, u64 vsesr) @@ -81,11 +91,27 @@ static inline unsigned long *vcpu_pc(const struct kvm_vcpu *vcpu) return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.pc; } -static inline unsigned long *vcpu_elr_el1(const struct kvm_vcpu *vcpu) +static inline unsigned long *__vcpu_elr_el1(const struct kvm_vcpu *vcpu) { return (unsigned long *)&vcpu_gp_regs(vcpu)->elr_el1; } +static inline unsigned long vcpu_read_elr_el1(const struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.sysregs_loaded_on_cpu) + return read_sysreg_el1(elr); + else + return *__vcpu_elr_el1(vcpu); +} + +static inline void vcpu_write_elr_el1(const struct kvm_vcpu *vcpu, unsigned long v) +{ + if (vcpu->arch.sysregs_loaded_on_cpu) + write_sysreg_el1(v, elr); + else + *__vcpu_elr_el1(vcpu) = v; +} + static inline unsigned long *vcpu_cpsr(const struct kvm_vcpu *vcpu) { return (unsigned long *)&vcpu_gp_regs(vcpu)->regs.pstate; @@ -135,13 +161,28 @@ static inline void vcpu_set_reg(struct kvm_vcpu *vcpu, u8 reg_num, vcpu_gp_regs(vcpu)->regs.regs[reg_num] = val; } -/* Get vcpu SPSR for current mode */ -static inline unsigned long *vcpu_spsr(const struct kvm_vcpu *vcpu) +static inline unsigned long vcpu_read_spsr(const struct kvm_vcpu *vcpu) { if (vcpu_mode_is_32bit(vcpu)) - return vcpu_spsr32(vcpu); + return vcpu_read_spsr32(vcpu); - return (unsigned long *)&vcpu_gp_regs(vcpu)->spsr[KVM_SPSR_EL1]; + if (vcpu->arch.sysregs_loaded_on_cpu) + return read_sysreg_el1(spsr); + else + return vcpu_gp_regs(vcpu)->spsr[KVM_SPSR_EL1]; +} + +static inline void vcpu_write_spsr(struct kvm_vcpu *vcpu, unsigned long v) +{ + if (vcpu_mode_is_32bit(vcpu)) { + vcpu_write_spsr32(vcpu, v); + return; + } + + if (vcpu->arch.sysregs_loaded_on_cpu) + write_sysreg_el1(v, spsr); + else + vcpu_gp_regs(vcpu)->spsr[KVM_SPSR_EL1] = v; } static inline bool vcpu_mode_priv(const struct kvm_vcpu *vcpu) @@ -282,15 +323,18 @@ static inline int kvm_vcpu_sys_get_rt(struct kvm_vcpu *vcpu) static inline unsigned long kvm_vcpu_get_mpidr_aff(struct kvm_vcpu *vcpu) { - return vcpu_sys_reg(vcpu, MPIDR_EL1) & MPIDR_HWID_BITMASK; + return vcpu_read_sys_reg(vcpu, MPIDR_EL1) & MPIDR_HWID_BITMASK; } static inline void kvm_vcpu_set_be(struct kvm_vcpu *vcpu) { - if (vcpu_mode_is_32bit(vcpu)) + if (vcpu_mode_is_32bit(vcpu)) { *vcpu_cpsr(vcpu) |= COMPAT_PSR_E_BIT; - else - vcpu_sys_reg(vcpu, SCTLR_EL1) |= (1 << 25); + } else { + u64 sctlr = vcpu_read_sys_reg(vcpu, SCTLR_EL1); + sctlr |= (1 << 25); + vcpu_write_sys_reg(vcpu, SCTLR_EL1, sctlr); + } } static inline bool kvm_vcpu_is_be(struct kvm_vcpu *vcpu) @@ -298,7 +342,7 @@ static inline bool kvm_vcpu_is_be(struct kvm_vcpu *vcpu) if (vcpu_mode_is_32bit(vcpu)) return !!(*vcpu_cpsr(vcpu) & COMPAT_PSR_E_BIT); - return !!(vcpu_sys_reg(vcpu, SCTLR_EL1) & (1 << 25)); + return !!(vcpu_read_sys_reg(vcpu, SCTLR_EL1) & (1 << 25)); } static inline unsigned long vcpu_data_guest_to_host(struct kvm_vcpu *vcpu, diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h index 596f8e414a4c..ab46bc70add6 100644 --- a/arch/arm64/include/asm/kvm_host.h +++ b/arch/arm64/include/asm/kvm_host.h @@ -272,9 +272,6 @@ struct kvm_vcpu_arch { /* IO related fields */ struct kvm_decode mmio_decode; - /* Interrupt related fields */ - u64 irq_lines; /* IRQ and FIQ levels */ - /* Cache some mmu pages needed inside spinlock regions */ struct kvm_mmu_memory_cache mmu_page_cache; @@ -287,10 +284,25 @@ struct kvm_vcpu_arch { /* Virtual SError ESR to restore when HCR_EL2.VSE is set */ u64 vsesr_el2; + + /* True when deferrable sysregs are loaded on the physical CPU, + * see kvm_vcpu_load_sysregs and kvm_vcpu_put_sysregs. */ + bool sysregs_loaded_on_cpu; }; #define vcpu_gp_regs(v) (&(v)->arch.ctxt.gp_regs) -#define vcpu_sys_reg(v,r) ((v)->arch.ctxt.sys_regs[(r)]) + +/* + * Only use __vcpu_sys_reg if you know you want the memory backed version of a + * register, and not the one most recently accessed by a running VCPU. For + * example, for userspace access or for system registers that are never context + * switched, but only emulated. + */ +#define __vcpu_sys_reg(v,r) ((v)->arch.ctxt.sys_regs[(r)]) + +u64 vcpu_read_sys_reg(struct kvm_vcpu *vcpu, int reg); +void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg); + /* * CP14 and CP15 live in the same array, as they are backed by the * same system registers. @@ -298,14 +310,6 @@ struct kvm_vcpu_arch { #define vcpu_cp14(v,r) ((v)->arch.ctxt.copro[(r)]) #define vcpu_cp15(v,r) ((v)->arch.ctxt.copro[(r)]) -#ifdef CONFIG_CPU_BIG_ENDIAN -#define vcpu_cp15_64_high(v,r) vcpu_cp15((v),(r)) -#define vcpu_cp15_64_low(v,r) vcpu_cp15((v),(r) + 1) -#else -#define vcpu_cp15_64_high(v,r) vcpu_cp15((v),(r) + 1) -#define vcpu_cp15_64_low(v,r) vcpu_cp15((v),(r)) -#endif - struct kvm_vm_stat { ulong remote_tlb_flush; }; @@ -358,10 +362,15 @@ int kvm_perf_teardown(void); struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr); +void __kvm_set_tpidr_el2(u64 tpidr_el2); +DECLARE_PER_CPU(kvm_cpu_context_t, kvm_host_cpu_state); + static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr, unsigned long hyp_stack_ptr, unsigned long vector_ptr) { + u64 tpidr_el2; + /* * Call initialization code, and switch to the full blown HYP code. * If the cpucaps haven't been finalized yet, something has gone very @@ -370,6 +379,16 @@ static inline void __cpu_init_hyp_mode(phys_addr_t pgd_ptr, */ BUG_ON(!static_branch_likely(&arm64_const_caps_ready)); __kvm_call_hyp((void *)pgd_ptr, hyp_stack_ptr, vector_ptr); + + /* + * Calculate the raw per-cpu offset without a translation from the + * kernel's mapping to the linear mapping, and store it in tpidr_el2 + * so that we can use adr_l to access per-cpu variables in EL2. + */ + tpidr_el2 = (u64)this_cpu_ptr(&kvm_host_cpu_state) + - (u64)kvm_ksym_ref(kvm_host_cpu_state); + + kvm_call_hyp(__kvm_set_tpidr_el2, tpidr_el2); } static inline void kvm_arch_hardware_unsetup(void) {} @@ -416,6 +435,13 @@ static inline void kvm_arm_vhe_guest_enter(void) static inline void kvm_arm_vhe_guest_exit(void) { local_daif_restore(DAIF_PROCCTX_NOIRQ); + + /* + * When we exit from the guest we change a number of CPU configuration + * parameters, such as traps. Make sure these changes take effect + * before running the host or additional guests. + */ + isb(); } static inline bool kvm_arm_harden_branch_predictor(void) @@ -423,4 +449,7 @@ static inline bool kvm_arm_harden_branch_predictor(void) return cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR); } +void kvm_vcpu_load_sysregs(struct kvm_vcpu *vcpu); +void kvm_vcpu_put_sysregs(struct kvm_vcpu *vcpu); + #endif /* __ARM64_KVM_HOST_H__ */ diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h index f26f9cd70c72..384c34397619 100644 --- a/arch/arm64/include/asm/kvm_hyp.h +++ b/arch/arm64/include/asm/kvm_hyp.h @@ -120,37 +120,38 @@ typeof(orig) * __hyp_text fname(void) \ return val; \ } -void __vgic_v2_save_state(struct kvm_vcpu *vcpu); -void __vgic_v2_restore_state(struct kvm_vcpu *vcpu); int __vgic_v2_perform_cpuif_access(struct kvm_vcpu *vcpu); void __vgic_v3_save_state(struct kvm_vcpu *vcpu); void __vgic_v3_restore_state(struct kvm_vcpu *vcpu); +void __vgic_v3_activate_traps(struct kvm_vcpu *vcpu); +void __vgic_v3_deactivate_traps(struct kvm_vcpu *vcpu); +void __vgic_v3_save_aprs(struct kvm_vcpu *vcpu); +void __vgic_v3_restore_aprs(struct kvm_vcpu *vcpu); int __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu); void __timer_enable_traps(struct kvm_vcpu *vcpu); void __timer_disable_traps(struct kvm_vcpu *vcpu); -void __sysreg_save_host_state(struct kvm_cpu_context *ctxt); -void __sysreg_restore_host_state(struct kvm_cpu_context *ctxt); -void __sysreg_save_guest_state(struct kvm_cpu_context *ctxt); -void __sysreg_restore_guest_state(struct kvm_cpu_context *ctxt); +void __sysreg_save_state_nvhe(struct kvm_cpu_context *ctxt); +void __sysreg_restore_state_nvhe(struct kvm_cpu_context *ctxt); +void sysreg_save_host_state_vhe(struct kvm_cpu_context *ctxt); +void sysreg_restore_host_state_vhe(struct kvm_cpu_context *ctxt); +void sysreg_save_guest_state_vhe(struct kvm_cpu_context *ctxt); +void sysreg_restore_guest_state_vhe(struct kvm_cpu_context *ctxt); void __sysreg32_save_state(struct kvm_vcpu *vcpu); void __sysreg32_restore_state(struct kvm_vcpu *vcpu); -void __debug_save_state(struct kvm_vcpu *vcpu, - struct kvm_guest_debug_arch *dbg, - struct kvm_cpu_context *ctxt); -void __debug_restore_state(struct kvm_vcpu *vcpu, - struct kvm_guest_debug_arch *dbg, - struct kvm_cpu_context *ctxt); -void __debug_cond_save_host_state(struct kvm_vcpu *vcpu); -void __debug_cond_restore_host_state(struct kvm_vcpu *vcpu); +void __debug_switch_to_guest(struct kvm_vcpu *vcpu); +void __debug_switch_to_host(struct kvm_vcpu *vcpu); void __fpsimd_save_state(struct user_fpsimd_state *fp_regs); void __fpsimd_restore_state(struct user_fpsimd_state *fp_regs); bool __fpsimd_enabled(void); +void activate_traps_vhe_load(struct kvm_vcpu *vcpu); +void deactivate_traps_vhe_put(void); + u64 __guest_enter(struct kvm_vcpu *vcpu, struct kvm_cpu_context *host_ctxt); void __noreturn __hyp_do_panic(unsigned long, ...); diff --git a/arch/arm64/include/asm/kvm_mmu.h b/arch/arm64/include/asm/kvm_mmu.h index 7faed6e48b46..082110993647 100644 --- a/arch/arm64/include/asm/kvm_mmu.h +++ b/arch/arm64/include/asm/kvm_mmu.h @@ -69,9 +69,6 @@ * mappings, and none of this applies in that case. */ -#define HYP_PAGE_OFFSET_HIGH_MASK ((UL(1) << VA_BITS) - 1) -#define HYP_PAGE_OFFSET_LOW_MASK ((UL(1) << (VA_BITS - 1)) - 1) - #ifdef __ASSEMBLY__ #include <asm/alternative.h> @@ -81,28 +78,19 @@ * Convert a kernel VA into a HYP VA. * reg: VA to be converted. * - * This generates the following sequences: - * - High mask: - * and x0, x0, #HYP_PAGE_OFFSET_HIGH_MASK - * nop - * - Low mask: - * and x0, x0, #HYP_PAGE_OFFSET_HIGH_MASK - * and x0, x0, #HYP_PAGE_OFFSET_LOW_MASK - * - VHE: - * nop - * nop - * - * The "low mask" version works because the mask is a strict subset of - * the "high mask", hence performing the first mask for nothing. - * Should be completely invisible on any viable CPU. + * The actual code generation takes place in kvm_update_va_mask, and + * the instructions below are only there to reserve the space and + * perform the register allocation (kvm_update_va_mask uses the + * specific registers encoded in the instructions). */ .macro kern_hyp_va reg -alternative_if_not ARM64_HAS_VIRT_HOST_EXTN - and \reg, \reg, #HYP_PAGE_OFFSET_HIGH_MASK -alternative_else_nop_endif -alternative_if ARM64_HYP_OFFSET_LOW - and \reg, \reg, #HYP_PAGE_OFFSET_LOW_MASK -alternative_else_nop_endif +alternative_cb kvm_update_va_mask + and \reg, \reg, #1 /* mask with va_mask */ + ror \reg, \reg, #1 /* rotate to the first tag bit */ + add \reg, \reg, #0 /* insert the low 12 bits of the tag */ + add \reg, \reg, #0, lsl 12 /* insert the top 12 bits of the tag */ + ror \reg, \reg, #63 /* rotate back */ +alternative_cb_end .endm #else @@ -113,24 +101,44 @@ alternative_else_nop_endif #include <asm/mmu_context.h> #include <asm/pgtable.h> +void kvm_update_va_mask(struct alt_instr *alt, + __le32 *origptr, __le32 *updptr, int nr_inst); + static inline unsigned long __kern_hyp_va(unsigned long v) { - asm volatile(ALTERNATIVE("and %0, %0, %1", - "nop", - ARM64_HAS_VIRT_HOST_EXTN) - : "+r" (v) - : "i" (HYP_PAGE_OFFSET_HIGH_MASK)); - asm volatile(ALTERNATIVE("nop", - "and %0, %0, %1", - ARM64_HYP_OFFSET_LOW) - : "+r" (v) - : "i" (HYP_PAGE_OFFSET_LOW_MASK)); + asm volatile(ALTERNATIVE_CB("and %0, %0, #1\n" + "ror %0, %0, #1\n" + "add %0, %0, #0\n" + "add %0, %0, #0, lsl 12\n" + "ror %0, %0, #63\n", + kvm_update_va_mask) + : "+r" (v)); return v; } #define kern_hyp_va(v) ((typeof(v))(__kern_hyp_va((unsigned long)(v)))) /* + * Obtain the PC-relative address of a kernel symbol + * s: symbol + * + * The goal of this macro is to return a symbol's address based on a + * PC-relative computation, as opposed to a loading the VA from a + * constant pool or something similar. This works well for HYP, as an + * absolute VA is guaranteed to be wrong. Only use this if trying to + * obtain the address of a symbol (i.e. not something you obtained by + * following a pointer). + */ +#define hyp_symbol_addr(s) \ + ({ \ + typeof(s) *addr; \ + asm("adrp %0, %1\n" \ + "add %0, %0, :lo12:%1\n" \ + : "=r" (addr) : "S" (&s)); \ + addr; \ + }) + +/* * We currently only support a 40bit IPA. */ #define KVM_PHYS_SHIFT (40) @@ -140,7 +148,11 @@ static inline unsigned long __kern_hyp_va(unsigned long v) #include <asm/stage2_pgtable.h> int create_hyp_mappings(void *from, void *to, pgprot_t prot); -int create_hyp_io_mappings(void *from, void *to, phys_addr_t); +int create_hyp_io_mappings(phys_addr_t phys_addr, size_t size, + void __iomem **kaddr, + void __iomem **haddr); +int create_hyp_exec_mappings(phys_addr_t phys_addr, size_t size, + void **haddr); void free_hyp_pgds(void); void stage2_unmap_vm(struct kvm *kvm); @@ -249,7 +261,7 @@ struct kvm; static inline bool vcpu_has_cache_enabled(struct kvm_vcpu *vcpu) { - return (vcpu_sys_reg(vcpu, SCTLR_EL1) & 0b101) == 0b101; + return (vcpu_read_sys_reg(vcpu, SCTLR_EL1) & 0b101) == 0b101; } static inline void __clean_dcache_guest_page(kvm_pfn_t pfn, unsigned long size) @@ -348,36 +360,95 @@ static inline unsigned int kvm_get_vmid_bits(void) return (cpuid_feature_extract_unsigned_field(reg, ID_AA64MMFR1_VMIDBITS_SHIFT) == 2) ? 16 : 8; } -#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR +#ifdef CONFIG_KVM_INDIRECT_VECTORS +/* + * EL2 vectors can be mapped and rerouted in a number of ways, + * depending on the kernel configuration and CPU present: + * + * - If the CPU has the ARM64_HARDEN_BRANCH_PREDICTOR cap, the + * hardening sequence is placed in one of the vector slots, which is + * executed before jumping to the real vectors. + * + * - If the CPU has both the ARM64_HARDEN_EL2_VECTORS cap and the + * ARM64_HARDEN_BRANCH_PREDICTOR cap, the slot containing the + * hardening sequence is mapped next to the idmap page, and executed + * before jumping to the real vectors. + * + * - If the CPU only has the ARM64_HARDEN_EL2_VECTORS cap, then an + * empty slot is selected, mapped next to the idmap page, and + * executed before jumping to the real vectors. + * + * Note that ARM64_HARDEN_EL2_VECTORS is somewhat incompatible with + * VHE, as we don't have hypervisor-specific mappings. If the system + * is VHE and yet selects this capability, it will be ignored. + */ #include <asm/mmu.h> +extern void *__kvm_bp_vect_base; +extern int __kvm_harden_el2_vector_slot; + static inline void *kvm_get_hyp_vector(void) { struct bp_hardening_data *data = arm64_get_bp_hardening_data(); - void *vect = kvm_ksym_ref(__kvm_hyp_vector); + void *vect = kern_hyp_va(kvm_ksym_ref(__kvm_hyp_vector)); + int slot = -1; - if (data->fn) { - vect = __bp_harden_hyp_vecs_start + - data->hyp_vectors_slot * SZ_2K; + if (cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR) && data->fn) { + vect = kern_hyp_va(kvm_ksym_ref(__bp_harden_hyp_vecs_start)); + slot = data->hyp_vectors_slot; + } - if (!has_vhe()) - vect = lm_alias(vect); + if (this_cpu_has_cap(ARM64_HARDEN_EL2_VECTORS) && !has_vhe()) { + vect = __kvm_bp_vect_base; + if (slot == -1) + slot = __kvm_harden_el2_vector_slot; } + if (slot != -1) + vect += slot * SZ_2K; + return vect; } +/* This is only called on a !VHE system */ static inline int kvm_map_vectors(void) { - return create_hyp_mappings(kvm_ksym_ref(__bp_harden_hyp_vecs_start), - kvm_ksym_ref(__bp_harden_hyp_vecs_end), - PAGE_HYP_EXEC); -} + /* + * HBP = ARM64_HARDEN_BRANCH_PREDICTOR + * HEL2 = ARM64_HARDEN_EL2_VECTORS + * + * !HBP + !HEL2 -> use direct vectors + * HBP + !HEL2 -> use hardened vectors in place + * !HBP + HEL2 -> allocate one vector slot and use exec mapping + * HBP + HEL2 -> use hardened vertors and use exec mapping + */ + if (cpus_have_const_cap(ARM64_HARDEN_BRANCH_PREDICTOR)) { + __kvm_bp_vect_base = kvm_ksym_ref(__bp_harden_hyp_vecs_start); + __kvm_bp_vect_base = kern_hyp_va(__kvm_bp_vect_base); + } + + if (cpus_have_const_cap(ARM64_HARDEN_EL2_VECTORS)) { + phys_addr_t vect_pa = __pa_symbol(__bp_harden_hyp_vecs_start); + unsigned long size = (__bp_harden_hyp_vecs_end - + __bp_harden_hyp_vecs_start); + + /* + * Always allocate a spare vector slot, as we don't + * know yet which CPUs have a BP hardening slot that + * we can reuse. + */ + __kvm_harden_el2_vector_slot = atomic_inc_return(&arm64_el2_vector_last_slot); + BUG_ON(__kvm_harden_el2_vector_slot >= BP_HARDEN_EL2_SLOTS); + return create_hyp_exec_mappings(vect_pa, size, + &__kvm_bp_vect_base); + } + return 0; +} #else static inline void *kvm_get_hyp_vector(void) { - return kvm_ksym_ref(__kvm_hyp_vector); + return kern_hyp_va(kvm_ksym_ref(__kvm_hyp_vector)); } static inline int kvm_map_vectors(void) diff --git a/arch/arm64/include/asm/lse.h b/arch/arm64/include/asm/lse.h index eec95768eaad..8262325e2fc6 100644 --- a/arch/arm64/include/asm/lse.h +++ b/arch/arm64/include/asm/lse.h @@ -4,8 +4,11 @@ #if defined(CONFIG_AS_LSE) && defined(CONFIG_ARM64_LSE_ATOMICS) +#include <linux/compiler_types.h> +#include <linux/export.h> #include <linux/stringify.h> #include <asm/alternative.h> +#include <asm/cpucaps.h> #ifdef __ASSEMBLER__ diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index 50fa96a49792..49d99214f43c 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -29,12 +29,6 @@ #include <asm/sizes.h> /* - * Allow for constants defined here to be used from assembly code - * by prepending the UL suffix only with actual C code compilation. - */ -#define UL(x) _AC(x, UL) - -/* * Size of the PCI I/O space. This must remain a power of two so that * IO_SPACE_LIMIT acts as a mask for the low bits of I/O addresses. */ diff --git a/arch/arm64/include/asm/mmu.h b/arch/arm64/include/asm/mmu.h index a050d4f3615d..dd320df0d026 100644 --- a/arch/arm64/include/asm/mmu.h +++ b/arch/arm64/include/asm/mmu.h @@ -21,6 +21,8 @@ #define USER_ASID_FLAG (UL(1) << USER_ASID_BIT) #define TTBR_ASID_MASK (UL(0xffff) << 48) +#define BP_HARDEN_EL2_SLOTS 4 + #ifndef __ASSEMBLY__ typedef struct { @@ -49,9 +51,13 @@ struct bp_hardening_data { bp_hardening_cb_t fn; }; -#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR +#if (defined(CONFIG_HARDEN_BRANCH_PREDICTOR) || \ + defined(CONFIG_HARDEN_EL2_VECTORS)) extern char __bp_harden_hyp_vecs_start[], __bp_harden_hyp_vecs_end[]; +extern atomic_t arm64_el2_vector_last_slot; +#endif /* CONFIG_HARDEN_BRANCH_PREDICTOR || CONFIG_HARDEN_EL2_VECTORS */ +#ifdef CONFIG_HARDEN_BRANCH_PREDICTOR DECLARE_PER_CPU_READ_MOSTLY(struct bp_hardening_data, bp_hardening_data); static inline struct bp_hardening_data *arm64_get_bp_hardening_data(void) diff --git a/arch/arm64/include/asm/module.h b/arch/arm64/include/asm/module.h index 4f766178fa6f..b6dbbe3123a9 100644 --- a/arch/arm64/include/asm/module.h +++ b/arch/arm64/include/asm/module.h @@ -39,6 +39,8 @@ struct mod_arch_specific { u64 module_emit_plt_entry(struct module *mod, void *loc, const Elf64_Rela *rela, Elf64_Sym *sym); +u64 module_emit_adrp_veneer(struct module *mod, void *loc, u64 val); + #ifdef CONFIG_RANDOMIZE_BASE extern u64 module_alloc_base; #else diff --git a/arch/arm64/include/asm/percpu.h b/arch/arm64/include/asm/percpu.h index 43393208229e..9234013e759e 100644 --- a/arch/arm64/include/asm/percpu.h +++ b/arch/arm64/include/asm/percpu.h @@ -16,7 +16,10 @@ #ifndef __ASM_PERCPU_H #define __ASM_PERCPU_H +#include <linux/preempt.h> + #include <asm/alternative.h> +#include <asm/cmpxchg.h> #include <asm/stack_pointer.h> static inline void set_my_cpu_offset(unsigned long off) @@ -197,6 +200,32 @@ static inline unsigned long __percpu_xchg(void *ptr, unsigned long val, return ret; } +/* this_cpu_cmpxchg */ +#define _protect_cmpxchg_local(pcp, o, n) \ +({ \ + typeof(*raw_cpu_ptr(&(pcp))) __ret; \ + preempt_disable(); \ + __ret = cmpxchg_local(raw_cpu_ptr(&(pcp)), o, n); \ + preempt_enable(); \ + __ret; \ +}) + +#define this_cpu_cmpxchg_1(ptr, o, n) _protect_cmpxchg_local(ptr, o, n) +#define this_cpu_cmpxchg_2(ptr, o, n) _protect_cmpxchg_local(ptr, o, n) +#define this_cpu_cmpxchg_4(ptr, o, n) _protect_cmpxchg_local(ptr, o, n) +#define this_cpu_cmpxchg_8(ptr, o, n) _protect_cmpxchg_local(ptr, o, n) + +#define this_cpu_cmpxchg_double_8(ptr1, ptr2, o1, o2, n1, n2) \ +({ \ + int __ret; \ + preempt_disable(); \ + __ret = cmpxchg_double_local( raw_cpu_ptr(&(ptr1)), \ + raw_cpu_ptr(&(ptr2)), \ + o1, o2, n1, n2); \ + preempt_enable(); \ + __ret; \ +}) + #define _percpu_read(pcp) \ ({ \ typeof(pcp) __retval; \ diff --git a/arch/arm64/include/asm/pgtable-hwdef.h b/arch/arm64/include/asm/pgtable-hwdef.h index cdfe3e657a9e..fd208eac9f2a 100644 --- a/arch/arm64/include/asm/pgtable-hwdef.h +++ b/arch/arm64/include/asm/pgtable-hwdef.h @@ -291,6 +291,7 @@ #define TCR_TBI0 (UL(1) << 37) #define TCR_HA (UL(1) << 39) #define TCR_HD (UL(1) << 40) +#define TCR_NFD1 (UL(1) << 54) /* * TTBR. diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h index fce604e3e599..767598932549 100644 --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@ -34,10 +34,12 @@ #ifdef __KERNEL__ +#include <linux/build_bug.h> +#include <linux/stddef.h> #include <linux/string.h> #include <asm/alternative.h> -#include <asm/fpsimd.h> +#include <asm/cpufeature.h> #include <asm/hw_breakpoint.h> #include <asm/lse.h> #include <asm/pgtable-hwdef.h> @@ -103,11 +105,19 @@ struct cpu_context { struct thread_struct { struct cpu_context cpu_context; /* cpu context */ - unsigned long tp_value; /* TLS register */ -#ifdef CONFIG_COMPAT - unsigned long tp2_value; -#endif - struct fpsimd_state fpsimd_state; + + /* + * Whitelisted fields for hardened usercopy: + * Maintainers must ensure manually that this contains no + * implicit padding. + */ + struct { + unsigned long tp_value; /* TLS register */ + unsigned long tp2_value; + struct user_fpsimd_state fpsimd_state; + } uw; + + unsigned int fpsimd_cpu; void *sve_state; /* SVE registers, if any */ unsigned int sve_vl; /* SVE vector length */ unsigned int sve_vl_onexec; /* SVE vl after next exec */ @@ -116,14 +126,17 @@ struct thread_struct { struct debug_info debug; /* debugging */ }; -/* - * Everything usercopied to/from thread_struct is statically-sized, so - * no hardened usercopy whitelist is needed. - */ static inline void arch_thread_struct_whitelist(unsigned long *offset, unsigned long *size) { - *offset = *size = 0; + /* Verify that there is no padding among the whitelisted fields: */ + BUILD_BUG_ON(sizeof_field(struct thread_struct, uw) != + sizeof_field(struct thread_struct, uw.tp_value) + + sizeof_field(struct thread_struct, uw.tp2_value) + + sizeof_field(struct thread_struct, uw.fpsimd_state)); + + *offset = offsetof(struct thread_struct, uw); + *size = sizeof_field(struct thread_struct, uw); } #ifdef CONFIG_COMPAT @@ -131,13 +144,13 @@ static inline void arch_thread_struct_whitelist(unsigned long *offset, ({ \ unsigned long *__tls; \ if (is_compat_thread(task_thread_info(t))) \ - __tls = &(t)->thread.tp2_value; \ + __tls = &(t)->thread.uw.tp2_value; \ else \ - __tls = &(t)->thread.tp_value; \ + __tls = &(t)->thread.uw.tp_value; \ __tls; \ }) #else -#define task_user_tls(t) (&(t)->thread.tp_value) +#define task_user_tls(t) (&(t)->thread.uw.tp_value) #endif /* Sync TPIDR_EL0 back to thread_struct for current */ @@ -227,9 +240,9 @@ static inline void spin_lock_prefetch(const void *ptr) #endif -int cpu_enable_pan(void *__unused); -int cpu_enable_cache_maint_trap(void *__unused); -int cpu_clear_disr(void *__unused); +void cpu_enable_pan(const struct arm64_cpu_capabilities *__unused); +void cpu_enable_cache_maint_trap(const struct arm64_cpu_capabilities *__unused); +void cpu_clear_disr(const struct arm64_cpu_capabilities *__unused); /* Userspace interface for PR_SVE_{SET,GET}_VL prctl()s: */ #define SVE_SET_VL(arg) sve_set_current_vl(arg) diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 0e1960c59197..6171178075dc 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -288,6 +288,12 @@ #define SYS_MAIR_EL1 sys_reg(3, 0, 10, 2, 0) #define SYS_AMAIR_EL1 sys_reg(3, 0, 10, 3, 0) +#define SYS_LORSA_EL1 sys_reg(3, 0, 10, 4, 0) +#define SYS_LOREA_EL1 sys_reg(3, 0, 10, 4, 1) +#define SYS_LORN_EL1 sys_reg(3, 0, 10, 4, 2) +#define SYS_LORC_EL1 sys_reg(3, 0, 10, 4, 3) +#define SYS_LORID_EL1 sys_reg(3, 0, 10, 4, 7) + #define SYS_VBAR_EL1 sys_reg(3, 0, 12, 0, 0) #define SYS_DISR_EL1 sys_reg(3, 0, 12, 1, 1) @@ -490,6 +496,7 @@ #define SCTLR_EL1_BUILD_BUG_ON_MISSING_BITS BUILD_BUG_ON((SCTLR_EL1_SET ^ SCTLR_EL1_CLEAR) != ~0) /* id_aa64isar0 */ +#define ID_AA64ISAR0_TS_SHIFT 52 #define ID_AA64ISAR0_FHM_SHIFT 48 #define ID_AA64ISAR0_DP_SHIFT 44 #define ID_AA64ISAR0_SM4_SHIFT 40 @@ -511,6 +518,7 @@ /* id_aa64pfr0 */ #define ID_AA64PFR0_CSV3_SHIFT 60 #define ID_AA64PFR0_CSV2_SHIFT 56 +#define ID_AA64PFR0_DIT_SHIFT 48 #define ID_AA64PFR0_SVE_SHIFT 32 #define ID_AA64PFR0_RAS_SHIFT 28 #define ID_AA64PFR0_GIC_SHIFT 24 @@ -568,6 +576,7 @@ #define ID_AA64MMFR1_VMIDBITS_16 2 /* id_aa64mmfr2 */ +#define ID_AA64MMFR2_AT_SHIFT 32 #define ID_AA64MMFR2_LVA_SHIFT 16 #define ID_AA64MMFR2_IESB_SHIFT 12 #define ID_AA64MMFR2_LSM_SHIFT 8 diff --git a/arch/arm64/include/asm/system_misc.h b/arch/arm64/include/asm/system_misc.h index 07aa8e3c5630..28893a0b141d 100644 --- a/arch/arm64/include/asm/system_misc.h +++ b/arch/arm64/include/asm/system_misc.h @@ -45,17 +45,6 @@ extern void __show_regs(struct pt_regs *); extern void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd); -#define show_unhandled_signals_ratelimited() \ -({ \ - static DEFINE_RATELIMIT_STATE(_rs, \ - DEFAULT_RATELIMIT_INTERVAL, \ - DEFAULT_RATELIMIT_BURST); \ - bool __show_ratelimited = false; \ - if (show_unhandled_signals && __ratelimit(&_rs)) \ - __show_ratelimited = true; \ - __show_ratelimited; \ -}) - int handle_guest_sea(phys_addr_t addr, unsigned int esr); #endif /* __ASSEMBLY__ */ diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h index 9e82dd79c7db..dfc61d73f740 100644 --- a/arch/arm64/include/asm/tlbflush.h +++ b/arch/arm64/include/asm/tlbflush.h @@ -60,6 +60,15 @@ __tlbi(op, (arg) | USER_ASID_FLAG); \ } while (0) +/* This macro creates a properly formatted VA operand for the TLBI */ +#define __TLBI_VADDR(addr, asid) \ + ({ \ + unsigned long __ta = (addr) >> 12; \ + __ta &= GENMASK_ULL(43, 0); \ + __ta |= (unsigned long)(asid) << 48; \ + __ta; \ + }) + /* * TLB Management * ============== @@ -117,7 +126,7 @@ static inline void flush_tlb_all(void) static inline void flush_tlb_mm(struct mm_struct *mm) { - unsigned long asid = ASID(mm) << 48; + unsigned long asid = __TLBI_VADDR(0, ASID(mm)); dsb(ishst); __tlbi(aside1is, asid); @@ -128,7 +137,7 @@ static inline void flush_tlb_mm(struct mm_struct *mm) static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr) { - unsigned long addr = uaddr >> 12 | (ASID(vma->vm_mm) << 48); + unsigned long addr = __TLBI_VADDR(uaddr, ASID(vma->vm_mm)); dsb(ishst); __tlbi(vale1is, addr); @@ -146,7 +155,7 @@ static inline void __flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, bool last_level) { - unsigned long asid = ASID(vma->vm_mm) << 48; + unsigned long asid = ASID(vma->vm_mm); unsigned long addr; if ((end - start) > MAX_TLB_RANGE) { @@ -154,8 +163,8 @@ static inline void __flush_tlb_range(struct vm_area_struct *vma, return; } - start = asid | (start >> 12); - end = asid | (end >> 12); + start = __TLBI_VADDR(start, asid); + end = __TLBI_VADDR(end, asid); dsb(ishst); for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12)) { @@ -185,8 +194,8 @@ static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end return; } - start >>= 12; - end >>= 12; + start = __TLBI_VADDR(start, 0); + end = __TLBI_VADDR(end, 0); dsb(ishst); for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12)) @@ -202,7 +211,7 @@ static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end static inline void __flush_tlb_pgtable(struct mm_struct *mm, unsigned long uaddr) { - unsigned long addr = uaddr >> 12 | (ASID(mm) << 48); + unsigned long addr = __TLBI_VADDR(uaddr, ASID(mm)); __tlbi(vae1is, addr); __tlbi_user(vae1is, addr); diff --git a/arch/arm64/include/asm/traps.h b/arch/arm64/include/asm/traps.h index 178e338d2889..c320f3bf6c57 100644 --- a/arch/arm64/include/asm/traps.h +++ b/arch/arm64/include/asm/traps.h @@ -35,10 +35,10 @@ struct undef_hook { void register_undef_hook(struct undef_hook *hook); void unregister_undef_hook(struct undef_hook *hook); -void force_signal_inject(int signal, int code, struct pt_regs *regs, - unsigned long address); - -void arm64_notify_segfault(struct pt_regs *regs, unsigned long addr); +void force_signal_inject(int signal, int code, unsigned long address); +void arm64_notify_segfault(unsigned long addr); +void arm64_force_sig_info(struct siginfo *info, const char *str, + struct task_struct *tsk); /* * Move regs->pc to next instruction and do necessary setup before it diff --git a/arch/arm64/include/asm/virt.h b/arch/arm64/include/asm/virt.h index c5f89442785c..9d1e24e030b3 100644 --- a/arch/arm64/include/asm/virt.h +++ b/arch/arm64/include/asm/virt.h @@ -102,12 +102,6 @@ static inline bool has_vhe(void) return false; } -#ifdef CONFIG_ARM64_VHE -extern void verify_cpu_run_el(void); -#else -static inline void verify_cpu_run_el(void) {} -#endif - #endif /* __ASSEMBLY__ */ #endif /* ! __ASM__VIRT_H */ diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h index f018c3deea3b..17c65c8f33cb 100644 --- a/arch/arm64/include/uapi/asm/hwcap.h +++ b/arch/arm64/include/uapi/asm/hwcap.h @@ -44,5 +44,9 @@ #define HWCAP_SHA512 (1 << 21) #define HWCAP_SVE (1 << 22) #define HWCAP_ASIMDFHM (1 << 23) +#define HWCAP_DIT (1 << 24) +#define HWCAP_USCAT (1 << 25) +#define HWCAP_ILRCPC (1 << 26) +#define HWCAP_FLAGM (1 << 27) #endif /* _UAPI__ASM_HWCAP_H */ diff --git a/arch/arm64/include/uapi/asm/siginfo.h b/arch/arm64/include/uapi/asm/siginfo.h index 9b4d91277742..574d12f86039 100644 --- a/arch/arm64/include/uapi/asm/siginfo.h +++ b/arch/arm64/include/uapi/asm/siginfo.h @@ -21,25 +21,4 @@ #include <asm-generic/siginfo.h> -/* - * SIGFPE si_codes - */ -#ifdef __KERNEL__ -#define FPE_FIXME 0 /* Broken dup of SI_USER */ -#endif /* __KERNEL__ */ - -/* - * SIGBUS si_codes - */ -#ifdef __KERNEL__ -#define BUS_FIXME 0 /* Broken dup of SI_USER */ -#endif /* __KERNEL__ */ - -/* - * SIGTRAP si_codes - */ -#ifdef __KERNEL__ -#define TRAP_FIXME 0 /* Broken dup of SI_USER */ -#endif /* __KERNEL__ */ - #endif |
